floriangardin
commited on
Commit
•
2a7dd08
1
Parent(s):
8934c00
musiclang/musiclang-chord-v2-4k
Browse files
README.md
CHANGED
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
- Loss: 0.
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -33,8 +33,8 @@ More information needed
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- learning_rate: 0.0001
|
36 |
-
- train_batch_size:
|
37 |
-
- eval_batch_size:
|
38 |
- seed: 444
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: cosine_with_restarts
|
@@ -46,10 +46,15 @@ The following hyperparameters were used during training:
|
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
-
| 0.
|
50 |
-
| 0.
|
51 |
-
| 0.
|
52 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
53 |
|
54 |
|
55 |
### Framework versions
|
|
|
13 |
|
14 |
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 0.5219
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- learning_rate: 0.0001
|
36 |
+
- train_batch_size: 32
|
37 |
+
- eval_batch_size: 32
|
38 |
- seed: 444
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: cosine_with_restarts
|
|
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| 0.9483 | 0.43 | 500 | 0.8710 |
|
50 |
+
| 0.7688 | 0.86 | 1000 | 0.7363 |
|
51 |
+
| 0.6949 | 1.28 | 1500 | 0.6479 |
|
52 |
+
| 0.6295 | 1.71 | 2000 | 0.5840 |
|
53 |
+
| 0.6093 | 2.14 | 2500 | 0.5532 |
|
54 |
+
| 0.5865 | 2.57 | 3000 | 0.5368 |
|
55 |
+
| 0.5559 | 2.99 | 3500 | 0.5281 |
|
56 |
+
| 0.5772 | 3.42 | 4000 | 0.5236 |
|
57 |
+
| 0.5641 | 3.85 | 4500 | 0.5219 |
|
58 |
|
59 |
|
60 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 22359920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ab2e818eb97f4da1e0c54b20ea841e80931ae83aacc4112259558b624d66210
|
3 |
size 22359920
|
runs/Jan30_17-33-51_cd32c414008c/events.out.tfevents.1706636032.cd32c414008c.2129.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e48ba5ff22112e34de393df6f672d576c344d36853e2c964c16edb6b1ec430db
|
3 |
+
size 43618
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cd186a68729b0ce6194aef9247ea56f77136ba167c63c438543fd1d6baf1167
|
3 |
size 4536
|